Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuanced
    -0.07
    >Please
    -0.06
    atak
    -0.06
     �
    -0.06
     phiếu
    -0.06
     kims
    -0.06
     Georges
    -0.06
    /cms
    -0.06
     Jin
    -0.06
    ￥
    -0.06
    POSITIVE LOGITS
     KERNEL
    0.07
    undai
    0.06
    Hash
    0.06
     buổi
    0.06
     zb
    0.06
    ?!
    0.06
    ateur
    0.06
     kidney
    0.06
    атків
    0.06
    Electric
    0.06
    Act Density 0.024%

    No Known Activations